feat: graph context injection — the session's prior knowledge, steered in at session start (vision-context-injection.md)
One shot per chat, fired at the first turn's onFinish: the session's topic (its only typed message) is embedded as an EmbeddingGemma retrieval query; the semantically closest graph propositions are selected under the session's token budget (pure budget, no similarity threshold — the decided doctrine) and delivered as a marker-only steer through the wake pipeline, queuing behind pending questions like every sub-agent result. - contracts: ChatSettings.graphContextTokens (default 1024, max 4096, step 128, 0 = off); GraphContextData + graphContextText; the graph-context JobKind + buildGraphContextSteer (id steer_ctx_<chatId>) - core/graph-context.ts: brute-force cosine top-K, greedy chars/4 fill under budget, most-recent UnderstandingLevel fold, count cap 64, parse-don't-cast at the marker seam - server: embedQuery (role-asymmetric query format, same warm singleton — vector-space parity by construction); the runner (startGraphContext- Injection one-shot gates; runGraphContextJob validates ledger parity); wake branches (chatIdOf/jobIdOf, finalizeJob done, recoverStaleJobs re-deliver or contextRespawn); abortJob kills context jobs SILENTLY (nothing was promised in the lesson); turn-service trigger seam - adapter: data-graph-context flattens to the canonical block (malformed parts have no model face) - UI: the budget slider (home dock + /chat/new draft, the session-data strip); the quiet SystemLine "~537 · 10 propositions"; dock kind "Knowledge context"; model-picker PUT now spreads settings (a model pick can no longer clear the sibling override) Live-smoked end to end on the real embedder + real GLM: seeded ledger (10 propositions), session on "modal logic: possible worlds and the necessity box" — job in the dock, queued behind the prober's question, delivered on the answer, SystemLine in the transcript, wake turn reads the block and continues the probe. Gates: tsc, lint, 459/459, build.
This commit is contained in:
amosblomqvist
@@ -10,7 +10,7 @@ import type { UIMessage } from "ai";
|
||||
import type { ThinkingLevel } from "@earendil-works/pi-agent-core";
|
||||
import type { Phase3 } from "../phases.ts";
|
||||
import type { PlanNodeStatus, PlanTree } from "./plan.ts";
|
||||
import type { EmissionStats } from "./graph.ts";
|
||||
import type { EmissionStats, UnderstandingLevel } from "./graph.ts";
|
||||
|
||||
// ─── Chat records (the session store's on-disk format) ───────────────────────
|
||||
|
||||
@@ -58,8 +58,23 @@ export interface ChatSettings {
|
||||
/** pi thinking level — must be in the chosen model's supported list
|
||||
* (getSupportedThinkingLevels; enforced by the settings route). */
|
||||
thinkingLevel?: ThinkingLevel;
|
||||
/** Graph context injection (vision-context-injection.md): the session's
|
||||
* token budget for the prior-knowledge block — the top semantically
|
||||
* closest propositions from the knowledge graph, injected once, at
|
||||
* session start, as a steer. Absent = the default (on); 0 = off. The
|
||||
* settings route enforces the range; the trigger (turn-service →
|
||||
* subagents/graph-context.ts) is one-shot, so a mid-session change
|
||||
* affects only sessions that haven't injected yet. */
|
||||
graphContextTokens?: number;
|
||||
}
|
||||
|
||||
/** The injection budget's decided knobs (2026-09-14): default 1024 (a
|
||||
* meaningful, modest slice of prior knowledge), hard max 4096, slider
|
||||
* step 128, 0 = off. */
|
||||
export const GRAPH_CONTEXT_TOKENS_DEFAULT = 1024;
|
||||
export const GRAPH_CONTEXT_TOKENS_MAX = 4096;
|
||||
export const GRAPH_CONTEXT_TOKENS_STEP = 128;
|
||||
|
||||
// ─── Background-extraction usage (the money channel, extraction side) ────────
|
||||
|
||||
/** One pipeline stage's model usage — the stage's model + every step it
|
||||
@@ -176,6 +191,54 @@ export const HANDOFF_TEXT =
|
||||
"The probe is concluded — the learner assessment is recorded. " +
|
||||
"Author the session's plan map now (call plan_init) and present it, then begin teaching.";
|
||||
|
||||
// ─── Graph context injection (vision-context-injection.md, 2026-09-14) ────────
|
||||
|
||||
/** One selected prior-knowledge proposition: similarity-ranked, annotated
|
||||
* with the learner's CURRENT understanding level — the fold is MOST
|
||||
* RECENT extraction instance (levels are per-instance, tied to moments in
|
||||
* time; the latest evidence is the best estimate of current understanding).
|
||||
* null = the node has no observation event at all. */
|
||||
export interface GraphContextProposition {
|
||||
id: string;
|
||||
statement: string;
|
||||
level: UnderstandingLevel | null;
|
||||
}
|
||||
|
||||
/** The data-graph-context part payload: what the UI renders (the counts)
|
||||
* AND the audit trail (the full block content — the transcript shows
|
||||
* exactly what was injected, and when). The model-facing text is derived
|
||||
* from this by graphContextText below — the adapter flattens the marker
|
||||
* part to it (the custom-message scheme: no authored human speech). */
|
||||
export interface GraphContextData {
|
||||
chatId: string;
|
||||
/** The session's budget at injection time (for the card's readout). */
|
||||
budget: number;
|
||||
/** Estimated tokens of the injected block — chars/4 heuristic. */
|
||||
tokens: number;
|
||||
/** The selected propositions, similarity-descending. */
|
||||
propositions: GraphContextProposition[];
|
||||
}
|
||||
|
||||
/** The model-facing block text — single-sourced (the adapter, the tests,
|
||||
* and reality can't drift). The level word travels with each line: the
|
||||
* closing gloss tells the agent what to do with each. */
|
||||
export function graphContextText(data: GraphContextData): string {
|
||||
const n = data.propositions.length;
|
||||
if (n === 0) return "";
|
||||
const lines = data.propositions.map(
|
||||
(p) => `- ${p.level ? `[${p.level}] ` : ""}${p.statement}`,
|
||||
);
|
||||
return [
|
||||
`Prior-knowledge context — what this learner already knows (from their knowledge graph, ` +
|
||||
`${n} proposition${n === 1 ? "" : "s"}, ~${data.tokens} tokens):`,
|
||||
"",
|
||||
...lines,
|
||||
"",
|
||||
"Treat this as reliable prior knowledge: build on what is solid, firm up what is shaky, " +
|
||||
"and teach around anything resisted. Do not re-teach solid ground.",
|
||||
].join("\n");
|
||||
}
|
||||
|
||||
export interface PlanBlockData {
|
||||
/** Only "full" survives (the 2026-09-11 pivot): the plan renders IN
|
||||
* FLOW once, at authoring. The neighborhood fragments are retired —
|
||||
|
||||
@@ -7,11 +7,11 @@
|
||||
* of "ai" (safe everywhere: server, client, tests). See docs/vision.md.
|
||||
*/
|
||||
import type { UIMessage } from "ai";
|
||||
import type { CallUsage } from "./chat.ts";
|
||||
import type { CallUsage, GraphContextData } from "./chat.ts";
|
||||
|
||||
// ─── Async sub-agent jobs (vision §2.5; plan.md Wave 0 protocol) ────────────
|
||||
|
||||
export type JobKind = "research" | "demo" | "visual";
|
||||
export type JobKind = "research" | "demo" | "visual" | "graph-context";
|
||||
export type JobStatus = "running" | "done" | "error";
|
||||
|
||||
export interface JobRecord {
|
||||
@@ -263,7 +263,11 @@ export interface AbortSteerMessage extends UIMessage {
|
||||
}
|
||||
|
||||
/** Anything the wake pipeline may queue and deliver. */
|
||||
export type SteerMessage = SubagentSteerMessage | AbortSteerMessage | ProbeHandoffSteerMessage;
|
||||
export type SteerMessage =
|
||||
| SubagentSteerMessage
|
||||
| AbortSteerMessage
|
||||
| ProbeHandoffSteerMessage
|
||||
| GraphContextSteerMessage;
|
||||
|
||||
/** Whether a result is the failure shape (html/svg empty, failure brief). */
|
||||
export function isSubagentFailure(kind: JobKind, result: ResearchResult | DemoResult | VisualResult): boolean {
|
||||
@@ -380,6 +384,34 @@ export function buildProbeHandoffSteer(chatId: string): ProbeHandoffSteerMessage
|
||||
};
|
||||
}
|
||||
|
||||
// ─── the graph-context steer (vision-context-injection.md) ───────────────────
|
||||
//
|
||||
// The injection's delivery: same wake pipeline, same gates — it queues
|
||||
// behind a pending quiz and rides the turn after the learner's answer, or
|
||||
// fires in the pump's idle window. Marker-only (the custom-message scheme):
|
||||
// no text part; the adapter flattens data-graph-context to graphContextText
|
||||
// (core/contracts/chat.ts owns the wording). One per chat, ever — the id is
|
||||
// deterministic per chat, so re-delivery is idempotent.
|
||||
|
||||
export interface GraphContextSteerMessage extends UIMessage {
|
||||
id: `steer_ctx_${string}`;
|
||||
role: "user";
|
||||
metadata: { graphContext: { chatId: string; jobId: string } };
|
||||
parts: [{ type: "data-graph-context"; data: GraphContextData }];
|
||||
}
|
||||
|
||||
export function buildGraphContextSteer(
|
||||
meta: { chatId: string; jobId: string },
|
||||
data: GraphContextData,
|
||||
): GraphContextSteerMessage {
|
||||
return {
|
||||
id: `steer_ctx_${meta.chatId}`,
|
||||
role: "user",
|
||||
metadata: { graphContext: meta },
|
||||
parts: [{ type: "data-graph-context", data }],
|
||||
};
|
||||
}
|
||||
|
||||
/** True when the transcript already carries this steer — idempotent
|
||||
* delivery for ANY steer kind: every steer id is deterministic per its
|
||||
* event (steer_<jobId> for jobs, steer_probe_<chatId> for the handoff). */
|
||||
|
||||
Reference in New Issue
Block a user